DF-Miner: Domain-specific facet mining by leveraging the hyperlink structure of Wikipedia

DF-Miner: Domain-specific facet mining by leveraging the hyperlink structure of Wikipedia
复制标题

DF-Miner:利用维基百科的超链接结构进行特定领域的方面挖掘

DOI:
10.1016/j.knosys.2015.01.001
复制
发表时间:
2015-03
影响因子:
8.8
通讯作者:
Bei Wu
Bei Wu
中科院分区:
计算机科学1区
文献类型:
--
作者:
Qinghua Zheng;Wei Zhang;Chenchen Wang;Bei Wu

文献摘要

参考文献

被引文献

相似文献

将一组特定领域的术语组织成一个有意义的层次结构是分面搜索和知识组织的一项重要任务。在本文中,我们提出了一种自动的方法,称为域特定方面(DF)-矿工,发现DF的超链接结构的基础上,在维基百科的文章页面。每个文章页面对应一个特定领域的术语。文章页面之间的超链接结构代表了这些术语之间的联系。特定领域术语集之间的联系的社区结构揭示了该领域的各个方面。具有更多连接的术语为刻面标注提供了重要线索。因此,DF-Miner首先从Wikipedia文章页面构建特定于域的超链接图。然后从维基百科分类页面中提取树结构。DF-Miner根据社区检测的结果将领域的术语分组为多个方面。最后,DF-Miner根据术语的连接数和从类别页面中提取的树结构为每个方面选择一个有意义的标签。使用六个真实世界的数据集进行了两个实验来评估DF-Miner。实验结果表明,DF-Miner的性能优于基于文本内容的方法。
Organizing a set of domain-specific terms into a meaningful hierarchical structure is an essential task for faceted search and knowledge organization. In this paper, we present an automatic approach, called domain-specific facet (DF)-Miner, to discover DFs based on the hyperlink structure within the Wikipedia article pages. Each article page corresponds to a domain-specific term. The hyperlink structures among article pages represent the connections among these terms. The community structure of the connections among a domain-specific term set reveals the facets of the domain. The terms with more connections provide important clues for facet labeling. Accordingly, DF-Miner first constructs a domain-specific hyperlink graph from the Wikipedia article pages. Then it extracts a tree structure from the Wikipedia category pages. DF-Miner groups the terms of a domain into multiple facets based on the result of community detection. Finally, DF-Miner selects a meaningful label for each facet based on the connection number of terms and the extracted tree structure from the category pages. Two experiments were conducted with six real-world datasets to evaluate DF-Miner. The experimental results show that DF-Miner performs better than the textual content-based approaches.
分面搜索调查
DOI: --
发表时间: 2013
影响因子: 0.8
作者:
Qinghua Zheng;Wei Zhang;Xiaoyu Fu;Boqin Feng
通讯作者: Boqin Feng
DOI: 10.1145/1281192.1281246
发表时间: 2007-08
影响因子: 8.7
作者:
Qiaozhu Mei;Xuehua Shen;ChengXiang Zhai
通讯作者: Qiaozhu Mei;Xuehua Shen;ChengXiang Zhai
DOI: 10.1145/1568292.1568295
发表时间: 2009-08
期刊: ACM Trans. Asian Lang. Inf. Process.
影响因子: --
作者:
Cam-Tu Nguyen;X. Phan;S. Horiguchi;Thu-Trang Nguyen;Quang-Thuy Ha
通讯作者: Cam-Tu Nguyen;X. Phan;S. Horiguchi;Thu-Trang Nguyen;Quang-Thuy Ha
DOI: 10.1145/1571941.1571967
发表时间: 2009-07
期刊: Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
影响因子: --
作者:
David Carmel;Haggai Roitman;Naama Zwerdling
通讯作者: David Carmel;Haggai Roitman;Naama Zwerdling
DOI: 10.1145/1482343.1482344
发表时间: 2009-03
期刊: ACM Trans. Asian Lang. Inf. Process.
影响因子: --
作者:
Chung-Hsien Wu;Haizhou Li
通讯作者: Chung-Hsien Wu;Haizhou Li